Improving Ultra-High b-value Prostate Diffusion Image Reconstruction at 3T
Neha Koonjoo1, Bo Zhu1,2, Danyal Bhutto1,2,3, Arnaud Guidon4, Matthew Christensen1,2, Mukesh Harisinghani1, and Matthew S Rosen1,2,5
1Department of Radiology, A.A Martinos Center for Biomedical Imaging / MGH, Charlestown, MA, United States, 2Harvard Medical School, Boston, MA, United States, 3Department of Biomedical Engineering, Boston University, Boston, MA, United States, 4GE Healthcare, Boston, MA, United States, 5Department of Physics, Harvard University, Cambridge, MA, United States
Ultra-high b-value Diffusion-weighted Prostate MR is gaining more attention in medical imaging, due to the non-invasiveness of imaging and to better contrast of malignant tissues as the lower diffusivity of water molecules can enable early diagnosis of cancer. The main drawback of MR at ultra-high b-value is the poor resultant SNR of the reconstructed images. We propose to improve the image quality of the prostate data acquired at b=2000 s/mm2 using a machine learning based reconstruction approach. Significant increase in signal intensities in the central gland and peripheral zone of the prostate was observed in healthy subjects.
This abstract and the presentation materials are available to members only;
a login is required.